Skip to content

Pull requests: alibaba/rtp-llm

New pull request New
22 Open 115 Closed
22 Open 115 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

feat: decode entrance support mtp
#245 opened Oct 16, 2025 by SJTUGavinLiu Loading…
4
feat: add vit support & multi-sequence generation for pd-sep
#244 opened Oct 16, 2025 by SJTUGavinLiu Loading…
4
feat: virtual memory allocation
#242 opened Oct 15, 2025 by ZhangZhiPku Loading…
feat: optimize apply rope with cache
#241 opened Oct 15, 2025 by Bruce-Lee-LY Loading…
feat: add remote update weight api.
#240 opened Oct 15, 2025 by ZhangZhiPku Loading…
2
optimize the implementation of per tensor fp8 moe token reordering
#239 opened Oct 15, 2025 by MMadhatter Loading…
feat: support grpc client config
#237 opened Oct 15, 2025 by wanglining97 Loading…
Feature/memory block cache
#233 opened Oct 15, 2025 by zhangchicc Loading…
1
refactor: use subprocess for multimodal preprocessing
#226 opened Oct 13, 2025 by ySingularity Loading…
29
feat: support reuse within queries
#224 opened Oct 13, 2025 by siluzhou Loading…
8
fix - fix mtp fake query and add check nan
#214 opened Oct 10, 2025 by zerozw Loading…
14
feat - frontend submit batch concurrently && batch scheduler support …
#208 opened Oct 10, 2025 by baowendin Loading…
5
feature - adapt deepseek in model py
#207 opened Oct 10, 2025 by Nancheng-11 Loading…
@netaddi
26
feat: add fastsafetensors loader
#205 opened Oct 10, 2025 by lixin010 Loading…
19
feat: optimizations for dense models on ROCM/AMD
#204 opened Oct 10, 2025 by DorianZi Loading…
30
feat: support moe for amd python refactored version
#199 opened Oct 9, 2025 by fff-2013 Loading…
17
fix: fix streams can not stop when num of return seq > 1
#191 opened Oct 9, 2025 by zhangjianning-zjn Loading…
2
feature - support return top_k of logits
#189 opened Oct 4, 2025 by jianglan89 Loading…
3
Add Qwen3 support for Arm
#145 opened Sep 2, 2025 by xiangze-arm Loading…
1
Add Deepseek V3 support for Arm
#144 opened Sep 2, 2025 by xiangze-arm Loading…
Flash attention implementation for Arm Device
#142 opened Aug 19, 2025 by xiangze-arm Loading…
1
add opt_125M
#103 opened Aug 15, 2024 by Nanuion Loading…
2
ProTip! Mix and match filters to narrow down what you’re looking for.